Sergey Levine

Robots can now learn and adapt in real-time, overcoming inference delays that previously stymied reinforcement learning effectiveness.

Action chunking's real power lies in its ability to create implicit ensembles, boosting robustness and generalization beyond traditional policy approaches.

Flow Reversal Steering transforms vague human commands into precise robotic actions, achieving up to 95% higher success rates in real-world tasks with minimal training.

QGF achieves superior performance in reinforcement learning by optimizing policies solely at test time, sidestepping the instability of traditional training methods.

An end-to-end learned robotic system can now clean your kitchen in a completely new house, thanks to a novel co-training approach on diverse data.